Senior Backend Software Engineer, AI Observability & Evals Platform (SF)

The role

You will build backend systems that power the LangSmith observability and evals platform. You will design, develop, and maintain backend services and APIs to support tracing, monitoring, and evaluation workflows.

What you will do

• Design, develop, and maintain backend services and APIs to support LangSmith’s tracing, monitoring, and evaluation workflows.
• Collaborate on architectural decisions to ensure systems are performant and maintainable.
• Optimize storage and query performance for high-volume observability and evaluation data.
• Ensure system reliability through strong testing, monitoring, and alerting practices.
• Troubleshoot and resolve production issues, performing root-cause analysis and implementing long-term fixes.
• Create and maintain technical documentation, including system design and API references.
• Work closely with full-stack engineers, product managers, and product designers on rolling out new features.

Required qualifications

• 5+ years of professional experience in backend engineering working on highly complex products
• Proficiency in one or more backend languages/frameworks
• Strong understanding of API design and building reliable data services.
• Experience with high-throughput or mission-critical systems.
• Demonstrated ability to optimize backend services for performance and reliability.
• Experience with database systems (Postgres, Redis, Clickhouse)
• Experience with cloud platforms (AWS, GCP, Azure)
• Strong communication skills
• Customer centricity and ownership mentality

Nice to have

• Python or Go
• Familiarity with fullstack or frontend engineering
• Performance tuning
• Debugging production issues

Benefits

• Medical, dental, and vision coverage
• Flexible vacation
• 401(k) plan
• Meals on in-office days in the US
• Variable compensation for relevant roles
• Meaningful equity

About the company

LangChain builds the foundation for agent engineering, offering a platform for building, evaluating, deploying, and operating AI agents at scale. Their platform includes LangSmith and open-source frameworks like LangChain and LangGraph.